@inproceedings{rohlfs-etal-2026-evaluators,
    title = "When Evaluators Cry Wolf: Lessons from Production {LLM}-as-Judge Evaluation in Educational {AI}",
    author = "Rohlfs, Chris  and
      Bosse, Rodrigo Vergara  and
      Hopper, Priscilla  and
      O{'}Keefe, Keanon  and
      Russell, Patrick J",
    editor = "Atanasova, Pepa  and
      Haffari, Gholamreza  and
      Wang, Minghan",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-industry.193/",
    pages = "3240--3255",
    ISBN = "979-8-89176-460-6"
}